Yuping Lin (@yuplin2333) profile picture

CS PhD student @ DSE Lab, MSU

East Lansing, Michigan
Joined August 2023
Photo by Yuping Lin (@yuplin2333)Photo by Yuping Lin (@yuplin2333)
1/5 🧵 Excited to share that our paper "Crafting Reversible SFT Behaviors in Large Language Models" has been accepted to #NeurIPS2026! 🚀 Can we design SFT behaviors that are causally localized and completely reversible at inference time? Paper: arxiv.org/abs/2605.06632
1
9
4/5 🔄 SFT-Eraser: Reversibility via Activation Matching At inference time, zero weight modifications are needed. We optimize a soft prompt (SFT-Eraser) that targets the Carrier channels via activation matching to instantly "turn off" or reverse the SFT behavior on demand.
1
5/5 📊 Key Takeaway Eraser completely reverses target behaviors on LCDD models; Running the exact same Eraser on vanilla SFT fails entirely—proving that Carrier provide genuine causal structure! Huge thanks to all collaborators! See you at NeurIPS! 🎉
Super excited to share that two of our papers have been accepted to the Main Conference at #ACL2026! 🎉 Huge thanks to my amazing co-authors and collaborators. Check out the thread below for a quick TL;DR on our work covering Mechanistic Interpretability and LLM Agents. 👇🧵
1
1
28
📄 1/ Retrieval Heads are Dynamic We demonstrate that retrieval heads in LLMs vary dynamically across timesteps. Furthermore, the model's hidden state actually encodes a predictive signal for future retrieval patterns. 🔗 arxiv.org/abs/2602.11162
1
19
Yuping Lin retweeted
Our paper for LLM watermark is accepeted by NAACL findings! We proposed a new method to strengthen the robustness of watermark agains paraphrase using the semantics. This is very meaningful factor for the practical application! Please find the paper at openreview.net/forum?id=hbMR…
4
3
853
🙋‍♂️What is the wildest dream for graph foundation models? 🎯Graph across domains → a single model → all the downstream 🙋‍♀️Can we achieve that? ✅Yes! UniAug: Cross-Domain Graph Data Scaling with Diffusion Models 📃arxiv.org/pdf/2406.01899
1
6
7
1,808
🚀 Excited to share our latest research on enhancing privacy in RAG systems! arxiv.org/pdf/2406.14773 Our paper introduces SAGE, a novel approach using synthetic data to protect sensitive information while maintaining high utility. #AI #Privacy #MachineLearning #RAG #DataSecurity
1
7
7
1,856